Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44342
    Prev
    Next
    INDEX
    Explanations

    specific numeric or symbolic identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ...
    -0.09
     .....
    -0.09
     ......
    -0.08
     [...]
    -0.08
     ....
    -0.08
     colourful
    -0.08
     ...↵
    -0.08
    Âħ
    -0.08
    --
    -0.08
     (...)
    -0.07
    POSITIVE LOGITS
     ’
    0.09
     Black
    0.08
     Blacks
    0.08
     Crush
    0.08
     Whites
    0.08
    [".
    0.07
     Ebony
    0.07
     damn
    0.07
     White
    0.06
     Harlem
    0.06
    Activations Density 0.002%

    No Known Activations